Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    http

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     stellen
    -0.07
     kraje
    -0.07
     cooker
    -0.06
     altru
    -0.06
    acht
    -0.06
    /net
    -0.06
    fair
    -0.06
    Lists
    -0.06
     Scal
    -0.06
    _clone
    -0.06
    POSITIVE LOGITS
    ----------------------------------------------------------------------
    0.07
    .createStatement
    0.06
    .GetFiles
    0.06
     ترك
    0.06
     deformation
    0.06
     tường
    0.06
    ------+
    0.06
    τι
    0.06
    ід
    0.06
     Дж
    0.06
    Act Density 0.001%

    No Known Activations